Comparison of Radiomic Features in a Diverse Cohort of Patients With Pancreatic Ductal Adenocarcinomas

Permuth, Jennifer B.; Vyas, Shraddha; Li, Jiannong; Chen, Dung-Tsa; Jeong, Daniel; Choi, Jung Woo

doi:10.3389/fonc.2021.712950

Cited by 11 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The participants in our internal dataset were entirely Asian patients, and the external dataset consisted of two different open-source datasets from the United States. The pancreatic content is one of the major factors influencing race/ethnicity differences [ 16 , 48 , 49 ]. Furthermore, diverse scanners at different institutions may also decrease sensitivity and accuracy.…”

Section: Discussionmentioning

confidence: 99%

Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study

Viriyasaranon

Chun

Lee

et al. 2023

Cancers

View full text Add to dashboard Cite

The aim of this study was to develop a novel deep learning (DL) model without requiring large-annotated training datasets for detecting pancreatic cancer (PC) using computed tomography (CT) images. This retrospective diagnostic study was conducted using CT images collected from 2004 and 2019 from 4287 patients diagnosed with PC. We proposed a self-supervised learning algorithm (pseudo-lesion segmentation (PS)) for PC classification, which was trained with and without PS and validated on randomly divided training and validation sets. We further performed cross-racial external validation using open-access CT images from 361 patients. For internal validation, the accuracy and sensitivity for PC classification were 94.3% (92.8–95.4%) and 92.5% (90.0–94.4%), and 95.7% (94.5–96.7%) and 99.3 (98.4–99.7%) for the convolutional neural network (CNN) and transformer-based DL models (both with PS), respectively. Implementing PS on a small-sized training dataset (randomly sampled 10%) increased accuracy by 20.5% and sensitivity by 37.0%. For external validation, the accuracy and sensitivity were 82.5% (78.3–86.1%) and 81.7% (77.3–85.4%) and 87.8% (84.0–90.8%) and 86.5% (82.3–89.8%) for the CNN and transformer-based DL models (both with PS), respectively. PS self-supervised learning can increase DL-based PC classification performance, reliability, and robustness of the model for unseen, and even small, datasets. The proposed DL model is potentially useful for PC diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study

Viriyasaranon

Chun

Lee

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…In distinguishing between high and low mesothelin expression in pancreatic cancer, it may imply that regions with high mesothelin expression have more textural diversity or grey level variation in the image, different from tissues with low mesothelin expression. An interesting nding [30] revealed that patients with higher GLCM values in the imaging histological features of pancreatic cancer had lower survival rates in different populations. This implies that radiological features are expected to be a surrogate for underlying biological factors that predict clinical outcomes, adding predictive value.…”

Section: Discussionmentioning

confidence: 99%

A Preliminary Study on Mesothelin Expression Levels in Pancreatic Cancer Using a CT Radiomics Model

Li,

Yang

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose To explore the feasibility of CT radiomics model in identifying the expression level of pancreatic mesothelin. Methods A retrospective analysis of 37 confirmed pancreatic cancer cases was conducted via surgical pathology. These cases had well-preserved tissue blocks and underwent upper abdominal CT scans within two weeks of surgery. Images, centered on the tumor's maximum diameter with one slice above and below the lesion, were selected for each case. Using 3D Slicer software, Regions of Interest (ROIs) were defined, and Pyradiomics extracted radiomics features. The dataset was categorized into positive and negative groups based on mesothelin immunohistochemical expression levels. Random division into training and testing sets ensued. Initial feature selection reduced radiomics dimensions, followed by secondary selection using (Least Absolute Shrinkage and Selection Operator) LASSO regression, resulting in a radiomics score model. Diagnostic performance was assessed in both sets using Receiver Operating Characteristic (ROC) analysis, precision via Calibration Curve (CC) analysis, and clinical benefit through Decision Curve Analysis (DCA). Results A total of 1218 radiomics features were extracted from 111 slices of CT scans in pancreatic cancer patients. The constructed radiomics model, after a series of dimensionality reduction and selection methods, achieved an Area Under the ROC Curve (AUC) of 0.84, sensitivity of 80.00%, and specificity of 75.68% in the training set. In the testing set, the AUC was 0.75, sensitivity was 58.82%, and specificity was 88.24%. The Calibration Curves (CC) in both the training and testing sets indicate a strong fit, while the Decision Curve Analysis (DCA) shows good clinical benefit. Conclusion A CT-based radiomics model can be used to evaluate pancreatic mesothelin expression levels, providing a reference for early prediction and differential diagnosis of pancreatic cancer using imaging techniques.

show abstract

“…A study comparing radiomics features in diverse populations with pancreatic ductal adenocarcinoma (PDAC) identified several textural radiomics features associated with unfavorable outcomes among Black patients with PDAC, independent of other prognostic factors such as tumor grade. The analytic dataset included cross sectional radiographs for 71 patients treated at a single institution [62].…”

Section: Radiomicsmentioning

confidence: 99%

Clinical Informatics Approaches to Understand and Address Cancer Disparities

2022

View full text Add to dashboard Cite

Objectives: Disparities in cancer incidence and outcomes across race, ethnicity, gender, socioeconomic status, and geography are well-documented, but their etiologies are often poorly understood and multifactorial. Clinical informatics can provide tools to better understand and address these disparities by enabling high-throughput analysis of multiple types of data. Here, we review recent efforts in clinical informatics to study and measure disparities in cancer. Methods: We carried out a narrative review of clinical informatics studies related to cancer disparities and bias published from 2018-2021, with a focus on domains such as real-world data (RWD) analysis, natural language processing (NLP), radiomics, genomics, proteomics, metabolomics, and metagenomics. Results: Clinical informatics studies that investigated cancer disparities across race, ethnicity, gender, and age were identified. Most cancer disparities work within clinical informatics used RWD analysis, NLP, radiomics, and genomics. Emerging applications of clinical informatics to understand cancer disparities, including proteomics, metabolomics, and metagenomics, were less well represented in the literature but are promising future research avenues. Algorithmic bias was identified as an important consideration when developing and implementing cancer clinical informatics techniques, and efforts to address this bias were reviewed. Conclusions: In recent years, clinical informatics has been used to probe a range of data sources to understand cancer disparities across different populations. As informatics tools become integrated into clinical decision-making, attention will need to be paid to ensure that algorithmic bias does not amplify existing disparities. In our increasingly interconnected medical systems, clinical informatics is poised to untap the full potential of multi-platform health data to address cancer disparities.

show abstract

Comparison of Radiomic Features in a Diverse Cohort of Patients With Pancreatic Ductal Adenocarcinomas

Cited by 11 publications

References 48 publications

Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study

Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study

A Preliminary Study on Mesothelin Expression Levels in Pancreatic Cancer Using a CT Radiomics Model

Clinical Informatics Approaches to Understand and Address Cancer Disparities

Contact Info

Product

Resources

About